Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3245
    Prev
    Next
    INDEX
    Explanations

    references to specific historical periods, particularly ones relating to decades in the 1960s and 1980s

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades, particularly the 1960s and 1980s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.65
     continu
    -0.64
     verbally
    -0.64
     deserving
    -0.62
    venge
    -0.61
    spons
    -0.61
    plan
    -0.59
    REDACTED
    -0.58
    Tickets
    -0.57
    Edge
    -0.57
    POSITIVE LOGITS
    s
    1.19
    sburg
    0.96
    -'
    0.93
    ties
    0.92
    eenth
    0.92
    sie
    0.91
    ixties
    0.88
    enthal
    0.87
    ies
    0.81
    sburgh
    0.79
    Activations Density 0.042%

    No Known Activations